INTERSPEECH 2010
11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Improving Monaural Speaker Identification by Double-Talk Detection

Rahim Saeidi (1), Pejman Mowlaee (2), Tomi Kinnunen (1), Zheng-Hua Tan (2), Mads Græsbøll Christensen (2), Søren Holdt Jensen (2), Pasi Fränti (1)

(1) University of Eastern Finland, Finland
(2) Aalborg University, Denmark

This paper describes a novel approach to improve monoaural speaker identification where two speakers are present in a single-microphone recording. The goal is to identify both of the underlying speakers in the given mixture. The proposed approach is composed of a double-talk detector (DTD) as a pre- processor and speaker identification back-end. We demonstrate that including the double-talk detector improves the speaker identification accuracy. Experiments on GRID corpus show that including the DTD improves average recognition accuracy from 96.53% to 97.43%.

Full Paper

Bibliographic reference.  Saeidi, Rahim / Mowlaee, Pejman / Kinnunen, Tomi / Tan, Zheng-Hua / Christensen, Mads Græsbøll / Jensen, Søren Holdt / Fränti, Pasi (2010): "Improving monaural speaker identification by double-talk detection", In INTERSPEECH-2010, 1069-1072.